gLRT1: Conduct a generalized logrank test for interval-censored data

In glrt: Generalized Logrank Tests for Interval-censored Failure Time Data

Description

Function gLRT1 conducts a k(>=2)-sample test for interval-censored survival data. The test is based on Zhao and Sun (2004). The null hypothesis is that all k survival functions of the failure time are the same, and the alternative hypothesis is that not all functions are the same.

Usage

gLRT1(A, k = 2, M = 50, EMstep = TRUE, ICMstep = TRUE, tol = 1e-06, 
maxiter = 1000, inf = Inf)

Arguments

A	an n by 3 data matrix with the censoring interval of the format (L, R] in columns 1 & 2 and treatmentment indicator ranging from 0 to k-1 in column 3.
k	number of treatments. The default is 2.
M	number of multiple imputations used in estimating the covariance of the test statistic. The default is 50.
EMstep	a boolean variable indicating whether to take an EM step in the iteration when estimating the common distribution function. The default is TRUE.
ICMstep	a boolean variable indicating whether to take an ICM step in the iteration when estimating the common distribution function. The default is TRUE.
tol	the maximal L_1 distance between successive estimates before stopping iteration when estimating the common distribution function. The default is 1.0e-6.
maxiter	the maximal number of iterations to perform before stopping when estimating the common distribution function. The default is 1000.
inf	value used in data for infinity. The default is Inf.

Details

Under the null hypothesis, the NPMLE of the common distribution function is computed by function ModifiedEMICM.

Censoring interval for each observation take the form (L_i, R_i]. For exact observations, L_i = R_i.

The estimated covariance of the test statistic depends on random resampling. It is normal that two runs of the test gLRT1 yield different test results.

The chi-square test used in gLRT1 has k-1 degrees of freedom.

Value

The function returns an object containing the following components:

method	test procedure used
u	the test statistic
v	the estimated covariance of the test statistic
chisq	the chisquare test statistic
df	the degrees of freedom of the test
p	p-value of the test

Author(s)

Qiang Zhao and Jianguo Sun

References

Q. Zhao and J. Sun (2004), "Generalized Log-rank Test for Mixed-Censored Failure Time Data", Statistics in Medicine, 23: 1621-1629.

Q. Zhao (2012), "gLRT - A New R Package for Analyzing Interval-censored Survival Data", Interval-Censored Time-to-Event Data: Methods and Applications, CRC Press, 377-396.

See Also

gLRT, gLRT2, gLRT3, gLRT4, ScoreTest

Examples

data(cosmesis)
gLRT1(cosmesis, inf=100)

data(diabetes)
gLRT1(diabetes, M=20)

Example output

Loading required package: survival
$method
[1] "Generalized log-rank test (Zhao and Sun, 2004)"

$u
[1] -9.141846  9.141846

$var
          [,1]      [,2]
[1,]  19.50083 -19.50083
[2,] -19.50083  19.50083

$chisq
        [,1]
[1,] 4.28563

$df
[1] 1

$p
           [,1]
[1,] 0.03843584

attr(,"row.names")
integer(0)
attr(,"class")
[1] "glrt1"
$method
[1] "Generalized log-rank test (Zhao and Sun, 2004)"

$u
[1]  22.69727 -22.69727

$var
          [,1]      [,2]
[1,]  151.3859 -151.3859
[2,] -151.3859  151.3859

$chisq
      [,1]
[1,] 3.403

$df
[1] 1

$p
           [,1]
[1,] 0.06507796

attr(,"row.names")
integer(0)
attr(,"class")
[1] "glrt1"

glrt documentation built on May 2, 2019, 8:31 a.m.